© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7786
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and interactions between people

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating conditions or continuations in complex thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.83
    favorite
    -0.75
    sed
    -0.69
    æ©
    -0.68
    hack
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    toggle
    -0.64
    Hide
    -0.63
    ãĤĬ
    -0.62
    Yep
    -0.61
    POSITIVE LOGITS
     we
    1.25
     please
    1.05
     regrett
    1.02
     hereby
    0.93
     irrespective
    0.93
     I
    0.93
     our
    0.92
     whilst
    0.89
     unfortunately
    0.86
     regardless
    0.86
    Activations Density 0.397%

    No Known Activations